Support DI in Linearization

[bvdmitri]

ReactiveMP.jl/src/approximations/linearization.jl

Line 19 in d2c8dde

struct Linearization <: AbstractApproximationMethod end

see ReactiveBayes/RxInfer.jl#509 (comment)

[gdalle]

Can you give me a little background on what linearization is used for? In particular, is there any way to leverage DI's preparation mechanism?

[Nimrais]

@gdalle However, the issue is completely different, and I am sorry that I am pinging you here. I wonder if you can take a look at another gradient-based method to run inference in RxInfer.jl https://reactivebayes.github.io/ExponentialFamilyProjection.jl/dev/#Examples. Basically, many models can be scaled far beyond just Linearisation.

But I think we are a bit naïve in our AD use yet and we are struggling to implement good default for it, here is the issue
ReactiveBayes/ExponentialFamilyProjection.jl#71.

However we have some small sucesses already https://reactivebayes.github.io/ExponentialFamilyProjection.jl/dev/#How-to-use-autograd-with-Gauss%E2%80%93Newton-(Enzyme.jl).

[wouterwln]

Hi! We are moving to a cleaner Epic -> Feature -> Task issue hierarchy to better organize our backlog.
This issue is currently either underspecified or not tagged appropriately.

To keep this issue open, please do the following within the next 7 days (by 25-11-2025):

1. Update/Replace: Ensure the description is clear and actionable.
2. Tag Correctly:For Tasks/Features, add the correct label (e.g., feature, task) AND include a link to the Parent Epic or Feature it belongs to.
3. For Bugs, add the Bug label. (Bugs do not require a parent link.)

Issues not updated, linked, or tagged correctly by the deadline will be closed and purged.

Thank you for helping us clean up and organize our backlog!